bert-nlp-project-google
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3628
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.0966 | 0.35 | 13 | 3.7392 |
3.7848 | 0.7 | 26 | 3.5830 |
3.6571 | 1.05 | 39 | 3.4920 |
3.5859 | 1.41 | 52 | 3.4435 |
3.5668 | 1.76 | 65 | 3.4769 |
3.5606 | 2.11 | 78 | 3.3831 |
3.5601 | 2.46 | 91 | 3.3910 |
3.468 | 2.81 | 104 | 3.3798 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.